© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93618
    Prev
    Next
    INDEX
    Explanations

    fibre

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fibre
    -0.94
     Fibre
    -0.88
    Fibre
    -0.73
    fibre
    -0.59
     Dart
    -0.54
     fiberglass
    -0.54
    Dart
    -0.53
    nbsp
    -0.52
    ardless
    -0.48
    utilisons
    -0.46
    POSITIVE LOGITS
     umane
    0.64
    book
    0.57
    ArrowToggle
    0.57
    hand
    0.57
    gate
    0.57
     vocale
    0.55
     espagne
    0.54
     normaux
    0.54
    mill
    0.54
    heads
    0.54
    Activations Density 0.144%

    No Known Activations